HuggingFaceTB / SmolLM3-3B-checkpoints

huggingface.co
Total runs: 8.1K
24-hour runs: 0
7-day runs: -935
30-day runs: -852
Model's Last Updated: August 15 2025

Introduction of SmolLM3-3B-checkpoints

Model Details of SmolLM3-3B-checkpoints

SmolLM3 Checkpoints

We are releasing intermediate checkpoints of SmolLM3 to enable further research.

Pre-training

We release checkpoints every 40,000 steps, which equals 94.4B tokens. The GBS (Global Batch Size) in tokens for SmolLM3-3B is 2,359,296. To calculate the number of tokens from a given step:

nb_tokens = nb_step * GBS
Training Stages

Stage 1: Steps 0 to 3,450,000 (86 checkpoints) config

Stage 2: Steps 3,450,000 to 4,200,000 (19 checkpoints) config

Stage 3: Steps 4,200,000 to 4,720,000 (13 checkpoints) config

image/png

Long Context Extension

For the additional 2 stages that extend the context length to 64k, we sample checkpoints every 4,000 steps (9.4B tokens) for a total of 10 checkpoints:

Long Context 4k to 32k config

Long Context 32k to 64k config

image/png

Post-training

We release checkpoints at every step of our post-training recipe: Mid training, SFT, APO soup, and LC expert.

image.png

How to Load a Checkpoint
# pip install transformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "HuggingFaceTB/SmolLM3-3B-checkpoints"
revision = "stage1-step-40000" # replace by the revision you want
device = torch.device("cuda" if torch.cuda.is_available() else "mps" if hasattr(torch, 'mps') and torch.mps.is_available() else "cpu")
tokenizer = AutoTokenizer.from_pretrained(checkpoint, revision=revision)
model = AutoModelForCausalLM.from_pretrained(checkpoint, revision=revision).to(device)
inputs = tokenizer.encode("Gravity is", return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
License

Apache 2.0

Runs of HuggingFaceTB SmolLM3-3B-checkpoints on huggingface.co

8.1K
Total runs
0
24-hour runs
-373
3-day runs
-935
7-day runs
-852
30-day runs

More Information About SmolLM3-3B-checkpoints huggingface.co Model

More SmolLM3-3B-checkpoints license Visit here:

https://choosealicense.com/licenses/apache-2.0

SmolLM3-3B-checkpoints huggingface.co

SmolLM3-3B-checkpoints huggingface.co is an AI model on huggingface.co that provides SmolLM3-3B-checkpoints's model effect (), which can be used instantly with this HuggingFaceTB SmolLM3-3B-checkpoints model. huggingface.co supports a free trial of the SmolLM3-3B-checkpoints model, and also provides paid use of the SmolLM3-3B-checkpoints. Support call SmolLM3-3B-checkpoints model through api, including Node.js, Python, http.

SmolLM3-3B-checkpoints huggingface.co Url

https://huggingface.co/HuggingFaceTB/SmolLM3-3B-checkpoints

HuggingFaceTB SmolLM3-3B-checkpoints online free

SmolLM3-3B-checkpoints huggingface.co is an online trial and call api platform, which integrates SmolLM3-3B-checkpoints's modeling effects, including api services, and provides a free online trial of SmolLM3-3B-checkpoints, you can try SmolLM3-3B-checkpoints online for free by clicking the link below.

HuggingFaceTB SmolLM3-3B-checkpoints online free url in huggingface.co:

https://huggingface.co/HuggingFaceTB/SmolLM3-3B-checkpoints

SmolLM3-3B-checkpoints install

SmolLM3-3B-checkpoints is an open source model from GitHub that offers a free installation service, and any user can find SmolLM3-3B-checkpoints on GitHub to install. At the same time, huggingface.co provides the effect of SmolLM3-3B-checkpoints install, users can directly use SmolLM3-3B-checkpoints installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

SmolLM3-3B-checkpoints install url in huggingface.co:

https://huggingface.co/HuggingFaceTB/SmolLM3-3B-checkpoints

Url of SmolLM3-3B-checkpoints

SmolLM3-3B-checkpoints huggingface.co Url

Provider of SmolLM3-3B-checkpoints huggingface.co

HuggingFaceTB
ORGANIZATIONS

Other API from HuggingFaceTB